Short Text Categorization in Python

This repository is a collection of algorithms for multi-class classification to short texts using Python. Modules are backward compatible unless otherwise specified. Feel free to give suggestions.

To install it, in a console, use pip.

>>> pip install -U shorttext

or, if you want the most updated code that is not released on PyPI yet, type

>>> pip install -U git+https://github.com/stephenhky/PyShortTextCategorization@master

Developers are advised to make sure Keras >=2 be installed. Users are advised to install the backend Tensorflow (preferred) or Theano in advance.

Before using, check the language model of spaCy has been installed or updated, by running:

>>> spacy download en

See tutorial for how to use the package.

Issues

To report any issues, go to the Issues tab of the Github page and start a thread. It is welcome for developers to submit pull requests on their own to fix any errors.

Useful Links

• Documentation: http://shorttext.readthedocs.io
• Github: https://github.com/stephenhky/PyShortTextCategorization
• PyPI: https://pypi.org/project/shorttext/
• "Short Text Mining using Advanced Keras Layers and Maxent: shorttext 0.4.1," WordPress
• "Python Package for Short Text Mining", WordPress
• "Document-Term Matrix: Text Mining in R and Python," WordPress
• An earlier version of this repository is a demonstration of the following blog post: Short Text Categorization using Deep Neural Networks and Word-Embedding Models

News

• 02/27/2018: shorttext 0.6.0 released.
• 01/19/2018: shorttext 0.5.11 released.
• 01/15/2018: shorttext 0.5.10 released.
• 12/14/2017: shorttext 0.5.9 released.
• 11/08/2017: shorttext 0.5.8 released.
• 10/27/2017: shorttext 0.5.7 released.
• 10/17/2017: shorttext 0.5.6 released.
• 09/28/2017: shorttext 0.5.5 released.
• 09/08/2017: shorttext 0.5.4 released.
• 09/02/2017: end of GSoC project. (Report)
• 08/22/2017: shorttext 0.5.1 released.
• 07/28/2017: shorttext 0.4.1 released.
• 07/26/2017: shorttext 0.4.0 released.
• 06/16/2017: shorttext 0.3.8 released.
• 06/12/2017: shorttext 0.3.7 released.
• 06/02/2017: shorttext 0.3.6 released.
• 05/30/2017: GSoC project (Chinmaya Pancholi, with gensim)
• 05/16/2017: shorttext 0.3.5 released.
• 04/27/2017: shorttext 0.3.4 released.
• 04/19/2017: shorttext 0.3.3 released.
• 03/28/2017: shorttext 0.3.2 released.
• 03/14/2017: shorttext 0.3.1 released.
• 02/23/2017: shorttext 0.2.1 released.
• 12/21/2016: shorttext 0.2.0 released.
• 11/25/2016: shorttext 0.1.2 released.
• 11/21/2016: shorttext 0.1.1 released.

Possible Future Updates

• Spelling corrections and fuzzy logic;
• Gradually replacing keras with direct TensorFlow or the keras package within TensorFlow;
• Jupyter notebooks as tutorials;
• Python 3 compatibility;
• More neural networks;
• More available corpus.